Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8890be9771be69e02157d292ce062e7059a7194a8554e5fc1e05bd2cb43efe56
+oid sha256:81e47e78eaa0ab1d7cf0e0db26eeeaa88d99a7a98f4797d4c0f1ce9089a6d187
 size 160086542

all_results.json

@@ -3,15 +3,15 @@
     "eval_accuracy": 0.86,
     "eval_f1_score": 0.8603998368013055,
     "eval_gmean": 0.8596058209945328,
-    "eval_loss": 0.27339842915534973,
+    "eval_loss": 0.2712109386920929,
     "eval_precision": 0.8614935064935065,
     "eval_recall": 0.86,
-    "eval_runtime": 308.5581,
-    "eval_samples_per_second": 0.324,
-    "eval_steps_per_second": 0.042,
+    "eval_runtime": 298.9366,
+    "eval_samples_per_second": 0.335,
+    "eval_steps_per_second": 0.043,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.3621236289419779,
-    "train_runtime": 19535.7167,
-    "train_samples_per_second": 0.269,
+    "train_loss": 0.370269775390625,
+    "train_runtime": 19024.4402,
+    "train_samples_per_second": 0.276,
     "train_steps_per_second": 0.004
 }

eval_results.json

@@ -3,10 +3,10 @@
     "eval_accuracy": 0.86,
     "eval_f1_score": 0.8603998368013055,
     "eval_gmean": 0.8596058209945328,
-    "eval_loss": 0.27339842915534973,
+    "eval_loss": 0.2712109386920929,
     "eval_precision": 0.8614935064935065,
     "eval_recall": 0.86,
-    "eval_runtime": 308.5581,
-    "eval_samples_per_second": 0.324,
-    "eval_steps_per_second": 0.042
+    "eval_runtime": 298.9366,
+    "eval_samples_per_second": 0.335,
+    "eval_steps_per_second": 0.043
 }

runs/Mar23_13-11-13_ecc28da32dbd/events.out.tfevents.1711199477.ecc28da32dbd.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5cb65fe765b397b804687e14947b8b2b924b225d87c684963a6d796ef9cca5
+size 12485

runs/Mar23_13-11-13_ecc28da32dbd/events.out.tfevents.1711218800.ecc28da32dbd.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ff4a1bfa1ae844b4633e9a0f307f48850938161c3634ee925ba909beeefb32
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.3621236289419779,
-    "train_runtime": 19535.7167,
-    "train_samples_per_second": 0.269,
+    "train_loss": 0.370269775390625,
+    "train_runtime": 19024.4402,
+    "train_samples_per_second": 0.276,
     "train_steps_per_second": 0.004
 }

trainer_state.json

@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 5.8125,
+      "grad_norm": 5.6875,
       "learning_rate": 1.8500000000000002e-05,
-      "loss": 0.3424,
+      "loss": 0.3936,
       "step": 8
     },
     {
@@ -20,39 +20,39 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27559569478034973,
+      "eval_loss": 0.27302733063697815,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 307.9009,
-      "eval_samples_per_second": 0.325,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 298.7097,
+      "eval_samples_per_second": 0.335,
+      "eval_steps_per_second": 0.044,
       "step": 8
     },
     {
       "epoch": 0.19,
-      "grad_norm": 6.15625,
+      "grad_norm": 7.25,
       "learning_rate": 1.65e-05,
-      "loss": 0.2941,
+      "loss": 0.3389,
       "step": 16
     },
     {
       "epoch": 0.19,
-      "eval_accuracy": 0.86,
-      "eval_f1_score": 0.8603998368013055,
-      "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27452147006988525,
-      "eval_precision": 0.8614935064935065,
-      "eval_recall": 0.86,
-      "eval_runtime": 308.1743,
-      "eval_samples_per_second": 0.324,
-      "eval_steps_per_second": 0.042,
+      "eval_accuracy": 0.87,
+      "eval_f1_score": 0.8705157155935307,
+      "eval_gmean": 0.8715093639362524,
+      "eval_loss": 0.2730761766433716,
+      "eval_precision": 0.8726060606060605,
+      "eval_recall": 0.87,
+      "eval_runtime": 298.9037,
+      "eval_samples_per_second": 0.335,
+      "eval_steps_per_second": 0.043,
       "step": 16
     },
     {
       "epoch": 0.29,
-      "grad_norm": 8.0,
+      "grad_norm": 6.3125,
       "learning_rate": 1.45e-05,
-      "loss": 0.4138,
+      "loss": 0.3385,
       "step": 24
     },
     {
@@ -60,19 +60,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27406251430511475,
+      "eval_loss": 0.2719433605670929,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 308.7677,
-      "eval_samples_per_second": 0.324,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 299.0682,
+      "eval_samples_per_second": 0.334,
+      "eval_steps_per_second": 0.043,
       "step": 24
     },
     {
       "epoch": 0.39,
-      "grad_norm": 7.59375,
+      "grad_norm": 8.375,
       "learning_rate": 1.25e-05,
-      "loss": 0.3497,
+      "loss": 0.3588,
       "step": 32
     },
     {
@@ -80,19 +80,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27359864115715027,
+      "eval_loss": 0.27156248688697815,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 307.8988,
-      "eval_samples_per_second": 0.325,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 298.8233,
+      "eval_samples_per_second": 0.335,
+      "eval_steps_per_second": 0.044,
       "step": 32
     },
     {
       "epoch": 0.49,
-      "grad_norm": 6.40625,
+      "grad_norm": 7.9375,
       "learning_rate": 1.0500000000000001e-05,
-      "loss": 0.2935,
+      "loss": 0.4425,
       "step": 40
     },
     {
@@ -100,19 +100,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.273681640625,
+      "eval_loss": 0.2713330090045929,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 307.426,
-      "eval_samples_per_second": 0.325,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 299.1918,
+      "eval_samples_per_second": 0.334,
+      "eval_steps_per_second": 0.043,
       "step": 40
     },
     {
       "epoch": 0.58,
-      "grad_norm": 7.25,
+      "grad_norm": 6.625,
       "learning_rate": 8.5e-06,
-      "loss": 0.3741,
+      "loss": 0.3521,
       "step": 48
     },
     {
@@ -120,19 +120,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27381837368011475,
+      "eval_loss": 0.271240234375,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 308.5186,
-      "eval_samples_per_second": 0.324,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 299.4172,
+      "eval_samples_per_second": 0.334,
+      "eval_steps_per_second": 0.043,
       "step": 48
     },
     {
       "epoch": 0.68,
-      "grad_norm": 6.96875,
+      "grad_norm": 4.875,
       "learning_rate": 6.5000000000000004e-06,
-      "loss": 0.41,
+      "loss": 0.409,
       "step": 56
     },
     {
@@ -140,19 +140,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.2735644578933716,
+      "eval_loss": 0.27153319120407104,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 307.8108,
-      "eval_samples_per_second": 0.325,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 298.9924,
+      "eval_samples_per_second": 0.334,
+      "eval_steps_per_second": 0.043,
       "step": 56
     },
     {
       "epoch": 0.78,
-      "grad_norm": 5.6875,
+      "grad_norm": 8.0,
       "learning_rate": 4.5e-06,
-      "loss": 0.4139,
+      "loss": 0.3119,
       "step": 64
     },
     {
@@ -160,19 +160,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27348631620407104,
+      "eval_loss": 0.27120116353034973,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 308.2439,
-      "eval_samples_per_second": 0.324,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 298.579,
+      "eval_samples_per_second": 0.335,
+      "eval_steps_per_second": 0.044,
       "step": 64
     },
     {
       "epoch": 0.88,
-      "grad_norm": 5.3125,
+      "grad_norm": 6.9375,
       "learning_rate": 2.5e-06,
-      "loss": 0.3477,
+      "loss": 0.3955,
       "step": 72
     },
     {
@@ -180,19 +180,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27347657084465027,
+      "eval_loss": 0.2712109386920929,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 307.7434,
-      "eval_samples_per_second": 0.325,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 298.6578,
+      "eval_samples_per_second": 0.335,
+      "eval_steps_per_second": 0.044,
       "step": 72
     },
     {
       "epoch": 0.97,
-      "grad_norm": 4.84375,
+      "grad_norm": 7.875,
       "learning_rate": 5.000000000000001e-07,
-      "loss": 0.3824,
+      "loss": 0.3467,
       "step": 80
     },
     {
@@ -200,21 +200,21 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27339842915534973,
+      "eval_loss": 0.2712109386920929,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 308.324,
-      "eval_samples_per_second": 0.324,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 298.9474,
+      "eval_samples_per_second": 0.335,
+      "eval_steps_per_second": 0.043,
       "step": 80
     },
     {
       "epoch": 1.0,
       "step": 82,
       "total_flos": 1.0505428534296576e+17,
-      "train_loss": 0.3621236289419779,
-      "train_runtime": 19535.7167,
-      "train_samples_per_second": 0.269,
+      "train_loss": 0.370269775390625,
+      "train_runtime": 19024.4402,
+      "train_samples_per_second": 0.276,
       "train_steps_per_second": 0.004
     }
   ],